Lifelong Learning for Sentiment Classification
This addresses the challenge of continuous learning in sentiment analysis, but it is incremental as it applies an existing LL approach to a specific domain.
The paper tackles the problem of lifelong learning for sentiment classification by proposing a Bayesian optimization framework based on stochastic gradient descent, and it shows that the method significantly outperforms baseline methods.
This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.